Pinned Loading

1. vllm vllm Public

   Forked from vllm-project/vllm

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python 1

2. LMCache LMCache Public

   Forked from LMCache/LMCache

   Supercharge Your LLM with the Fastest KV Cache Layer

   Python

3. production-stack production-stack Public

   Forked from FlowGPT/production-stack

   vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization

   Python

4. mms mms Public

   Forked from alpa-projects/mms

   AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23) AdaptServe: Auto-Scalable DL Serving with Dynamic Model Parallelism (HPSC 25)

   Jupyter Notebook

5. kvcache-hit-rate-calculator kvcache-hit-rate-calculator Public

   Computing the theoretical KVCache hit rate in the LLM serving system.

   Python 1

6. llm-inference-benchmarking llm-inference-benchmarking Public

   Forked from FlowGPT/llm-inference-benchmarking

   Python 1 1